Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5251 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.9136. Min Act: -0.0001
Data Index: 1569081 (Python Code)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.4131. Min Act: -0.0000
Data Index: 1586831 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.4080. Min Act: -0.0001
Data Index: 1436973 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.7123. Min Act: -0.0001
Data Index: 1538069 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.2241. Min Act: -0.0001
Data Index: 1505693 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.2785. Min Act: -0.0000
Data Index: 1395721 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.0814. Min Act: -0.0001
Data Index: 1634984 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.0687. Min Act: -0.0001
Data Index: 1582495 (Python Code)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9136. Min Range: -3.9136
Max Act: 3.1557. Min Act: -0.0001
Data Index: 1631295 (Python Code)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.6507. Min Act: -0.0001
Data Index: 1476989 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.7448. Min Act: -0.0001
Data Index: 1411121 (Python Code)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.9935. Min Act: -0.0001
Data Index: 1438793 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.6590. Min Act: -0.0001
Data Index: 1572815 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.7319. Min Act: -0.0001
Data Index: 1621569 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.7562. Min Act: -0.0001
Data Index: 1552497 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.5654. Min Act: -0.0001
Data Index: 1374941 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.6003. Min Act: -0.0000
Data Index: 1519416 (Python Code)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.5864. Min Act: -0.0001
Data Index: 1370993 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.5679. Min Act: -0.0001
Data Index: 1366631 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9136. Min Range: -3.9136
Max Act: 2.5672. Min Act: -0.0001
Data Index: 1388622 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19